Client Report - Can You Predict That?

On this page

• QUESTION

import pandas as pd 
import numpy as np
from lets_plot import *
# add the additional libraries you need to import for ML here
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix

LetsPlot.setup_html(isolated_frame=True)

# import your data here using pandas and the URL
df = pd.read_csv("https://raw.githubusercontent.com/byuidatascience/data4dwellings/master/data-raw/dwellings_ml/dwellings_ml.csv")

QUESTION

Build a classification model labeling houses as being built “before 1980” or “during or after 1980”. Your goal is to reach or exceed 90% accuracy. Report your final model choice and any other model parameters you may have tweaked (train-test split ratio, tuning parameters, etc).

The machine model is being trained and successful making the prediction if the house is build before 1980 with the precision of 93% as shown in the output below. When looking at the bar chart, we can see the importance of the features of the house make the critical decision for the model to predict the year that the house was built.

# Include and execute your code here
df = df[df["yrbuilt"].notna()]
y = df["before1980"]

X = df.drop(columns=["before1980", "yrbuilt"])
X = X.select_dtypes(include="number")

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.20, random_state=42, stratify=y
)

my_classifier = RandomForestClassifier()
my_classifier.fit(X_train, y_train)

pred = my_classifier.predict(X_test)

print(classification_report(y_test, pred))

my_classifier.feature_importances_
X_train.columns

df = pd.DataFrame({'importance':my_classifier.feature_importances_,
'feature':X_train.columns}).sort_values('importance')

p = (
    ggplot(data=df)
    + geom_bar(aes(x='feature', y='importance'), stat='identity')   # swapped x/y
    + coord_flip()  # keep horizontal look if you still want features on y visually
    + labs(
        x='Importance',
        y='Features',
        title='Factors that train the model',
        subtitle='Prediction of whether the house was built\nbefore 1980',
        caption='Source: Denver Open Data Catalog'
    )
)
p

              precision    recall  f1-score   support

           0       0.90      0.91      0.91      1719
           1       0.94      0.94      0.94      2864

    accuracy                           0.93      4583
   macro avg       0.92      0.92      0.92      4583
weighted avg       0.93      0.93      0.93      4583

accuracy = accuracy_score(y_test, pred)
precision = precision_score(y_test, pred, average='weighted')
recall = recall_score(y_test, pred, average='weighted')
f1 = f1_score(y_test, pred, average='weighted')
cm = confusion_matrix(y_test, pred)

print(f"Accuracy: {accuracy:.2f}")
print(f"Precision: {precision:.2f}")
print(f"Recall: {recall:.2f}")
print(f"F1 Score: {f1:.2f}")
print("Confusion Matrix:")
print(cm)

Accuracy: 0.93
Precision: 0.93
Recall: 0.93
F1 Score: 0.93
Confusion Matrix:
[[1560  159]
 [ 168 2696]]